StreamClarify: Proactive Clarification for Grounded Streaming Video Question Answering
cs.CV
Submitted: 2026-10-31
Updated: 2026-10-31
Terminology
Sources
- LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training
- Qwen3-VL Technical Report
- Hallucination of Multimodal Large Language Models: A Survey
- StreamingTOM: Streaming Token Compression for Efficient Video Understanding
- StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and Compression
- TUBench: Benchmarking Large Vision-Language Models on Trustworthiness with Unanswerable Questions
- Language Models (Mostly) Know What They Know
- V-Rex: Real-Time Streaming Video LLM Acceleration via Dynamic KV Cache Retrieval
- StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding
- A Survey on Hallucination in Large Vision-Language Models
- LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval
- CacheFlow: Compressive Streaming Memory for Efficient Long-Form Video Understanding
- OpenAI GPT-5 System Card
- SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- StreamingVLM: Real-Time Understanding for Infinite Video Streams
- Qwen3 Technical Report
- StreamAgent: Towards Anticipatory Agents for Streaming Video Understanding
- MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe
- WeaveTime: Stream from Earlier Frames into Emergent Memory in VideoLLMs
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs